基于自适应特征增强和融合的舰载机着舰拉制状态识别  

Landing State Recognition of Carrier-Based Aircraft Based onAdaptive Feature Enhancement and Fusion

作　　者：王可[1,2,3] 刘奕阳 杨杰[1] 鲁爱国 李哲[1] 徐明亮[1,2,3] WANG Ke;LIU Yiyang;YANG Jie;LU Aiguo;LI Zhe;XU Mingliang(School of Computer and Artificial Intelligence,Zhengzhou University,Zhengzhou 450001,China;National Supercomputing Center in Zhengzhou,Zhengzhou 450001,China;Intelligent Swarm System Engineering Research Center of the Ministry of Education,Zhengzhou 450001,China;Wuhan Digital Engineering Institute,Wuhan 430074,China)

机构地区：[1]郑州大学计算机与人工智能学院,郑州450001 [2]国家超级计算郑州中心,郑州450001 [3]智能集群系统教育部工程研究中心,郑州450001 [4]武汉数字工程研究所,武汉430074

出　　处：《上海交通大学学报》2025年第2期274-282,共9页Journal of Shanghai Jiaotong University

基　　金：国家自然科学基金(62036010);国防科技工业海洋防务技术创新中心创新基金(JJ-2022-709-01);中国博士后科学基金(2020M682348);河南省自然科学基金(232300421235)资助项目。

摘　　要：拉制状态识别能辅助着舰信号官及时准确地形成后续指挥决策,是舰载机着舰引导的重要环节.提出一种基于自适应特征增强和融合的拉制状态识别方法,包含基于注意力机制的特征增强模块,通过分割特征图、串联空间域和通道域增强视觉表征能力;利用多尺度特征融合模块,将高分辨率浅层特征与语义信息丰富的深层特征进行融合,充分利用上下文语义信息.基于所提方法,设计基于可穿戴增强现实设备的着舰拉制状态识别原型系统;构建着舰作业虚实融合数据集以评估方法性能.结果表明,所提算法综合性能优于基线算法,能满足拉制状态识别的应用需求.The recognition of engagement state aids landing signal officers in formulating command decisions promptly and precisely,which is crucial for guiding carrier-based aircraft landings.A method is proposed for recognizing the engagement state,leveraging adaptive feature enhancement and fusion,which includes an attention mechanism-based feature enhancement module and a multi-scale feature fusion module.The front module enhances visual representation by segmenting feature maps and concatenating spatial and channel domains,and the back module merges high-resolution shallow features with semantically rich deep features to fully utilize contextual information.A prototype system is developed to recognize landing engagement states based on the wearable augmented reality devices.To evaluate the performance of the method proposed,hybrid datasets of landing operations are constructed.The results show that the proposed algorithm outperforms baseline algorithms and meets the application requirements of engagement state recognition.

关 键 词：舰载机 阻拦着舰 特征融合 注意力机制 状态识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]